🔑 Claude Code for $0 — and the "AUTH Error" That Was Never the API Key

Tutorials & Methods
, ,
1

:key: That AUTH Error is lying. Your API key is almost never the problem — the session is stale, or your model can’t do the job. Two curls tell you which.

:puzzle_piece: Free Claude Code = a middleman app on your PC. Claude Code phones Anthropic; this answers the call itself and asks NVIDIA’s free models instead. Same terminal, $0 instead of $240/year.

:warning: Straight up: this does not hand you Claude. You keep the Claude Code tool — the thinking comes from someone else’s model.

🧠 What this actually is, in 30 seconds — no background needed

Claude Code is Anthropic’s coding assistant that lives in your terminal — it reads your files, writes code, runs commands, fixes its own mistakes. It normally costs $20/month (Pro) up to $200/month (Max).

Free Claude Code (FCC) is a small program you run on your own machine. Claude Code sends every request to Anthropic’s servers — FCC quietly stands in the middle, catches those requests, and forwards them to a different AI company that has a free tier. Claude Code never notices the swap.

├─ :white_check_mark: You keep: the terminal, the file editing, the agent behaviour, /commands, everything
├─ :counterclockwise_arrows_button: You swap: the brain — NVIDIA, DeepSeek, Gemini, Groq, Kimi, MiniMax, Z.ai, or a model on your own PC (Ollama / LM Studio / llama.cpp). 28 providers, switch anytime
└─ :cross_mark: You don’t get: actual Claude models. Nobody gives those away

:star: MIT licensed · 42,000+ stars · shipping updates the same week. It also launches Codex and Pi the same way (fcc-codex, fcc-pi).

⚡ The fix — changing the model mid-session does nothing

A live Claude session stays glued to whatever model it booted with. Pick a new one from the menu and it keeps hammering the old, dead one — throwing errors that look like auth failures.

# 1. exit Claude completely  (not a new tab — fully out)
# 2. restart the proxy
fcc-server restart
# 3. brand-new session
fcc-claude

First message to prove it’s alive:

Reply with exactly: FCC is working

:unlocked: Second cause, same symptom — and it’s FCC’s most-reported bug. If you ever logged into claude.ai from the terminal, that saved login outranks your proxy token. You get:

Auth conflict: Both a token (ANTHROPIC_AUTH_TOKEN) and an API key (/login managed key) are set.
API Error: 401 {"detail":"Invalid API key"}

Your key is fine. One command clears it:

claude /logout

…then relaunch with fcc-claude. :adhesive_bandage: Also check cat ~/.claude/settings.json | jq .env — a value saved in that file silently beats anything you export in your shell.

🩺 Two curls that split the blame in 10 seconds — key vs proxy

① Is my NVIDIA key good?

curl -s -o /dev/null -w "%{http_code}\n" \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  https://integrate.api.nvidia.com/v1/models

200 → key is fine, account is fine. Stop making new keys. · 401 → no key sent · 403 → key rejected or that model isn’t granted to you — 403 alone can’t tell you which.

② Is the proxy actually answering?

curl -X POST "http://localhost:8082/v1/messages" \
  -H "Authorization: Bearer freecc" -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-sonnet-4-6","max_tokens":1,"messages":[{"role":"user","content":"."}]}'

Anything starting {"id":"msg_ → working. Even an unknown-model error counts as a pass — it authenticated you before rejecting the name.

:bullseye: Both curls green but Claude Code still 401s? Then it’s the stale session above, 100%. :warning: ANTHROPIC_BASE_URL must be the root — http://localhost:8082, no /v1. Claude Code adds that itself.

🧨 The model trap — anything named "coder" quietly breaks it

Claude Code needs tool calling — the model’s ability to actually run commands and edit files, not just talk about them. Without it you get the worst kind of failure: no error at all. Claude describes what it’s about to do, prints tool JSON as plain text, and never touches a single file.

:skull_and_crossbones: Trap: models with coder, codellama, starcoder, codestral or granite-code in the name are mostly 2023-era builds from before tool calling existed. They’re the obvious-looking pick in the catalog and they’re the wrong one — deepseek-coder-6.7b-instruct is exactly this.

:white_check_mark: Picks that work:
├─ nvidia/nemotron-3-super-120b-a12b — FCC’s default, tool calling confirmed (120B total brain, 12B used per answer — fast for its size)
├─ minimaxai/minimax-m2.7 — the one with a confirmed working Claude-Code-on-NIM report; switch to it the moment tools stop firing
└─ :clipboard: Full live list: integrate.api.nvidia.com/v1/models — 118 models, no key needed to look

:microscope: That list carries zero capability info — presence proves nothing. Smoke-test any model before you trust it. Context limits: NVIDIA’s docs claim up to 1M, sibling models measured ~131K — test your own ceiling.

🚀 Full setup from zero — install, run, Linux needs two terminals 
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh

Same command updates it later. Add --dry-run first to see what it does without doing it.

:package: It also installs Claude Code and Codex, and offers Pi — not a single-package install. It pulls its own Python 3.14 through uv; on Ubuntu that’s expected, not a bug. It refuses to run while any fcc-* process is alive.

fcc-server     # terminal 1 — leave it open, this IS the proxy
fcc-claude     # terminal 2 — your Claude Code session

:desktop_computer: No tray icon on Linux — that’s Windows/macOS only, so two terminals is normal, not a broken install.
:gear: Paste your NVIDIA key into the admin panel: http://127.0.0.1:8082/admin (your PC only, nobody else can reach it).
:key: Get the key free at build.nvidia.com.

Real commands are fcc-server fcc-claude fcc-codex fcc-pi. (fcc-init and free-claude-code aren’t commands — you’ll get command-not-found.)

⚠️ Read before you start — phone gate, blocked countries, rate limit, terms

├─ :mobile_phone: No credit card — but a phone number is mandatory. NVIDIA sends an SMS code before it’ll issue a key.
├─ :prohibited: Country blocks on that SMS step: TR, IR, SY, CU, KP, RU, BY. If you’re in one, you hit a wall at the key step — use a different provider in FCC instead (OpenRouter, Gemini, Groq, Cerebras all have free tiers).
├─ :turtle: ~40 requests per minute is the real free-tier ceiling. No official way to raise it. Old “1,000 credits” numbers floating around are years stale.
├─ :open_book: Terms: NVIDIA keeps what you send and what comes back to improve their models, and the free API is for testing and evaluation — not production. So: personal projects, learning, messing around :white_check_mark: · client code, anything under NDA :cross_mark:
└─ :fire_extinguisher: Never overwrite ~/.claude.json with a fresh file — merge into it, or you wipe your whole Claude Code config.

💡 Five moments this actually saves you

├─ :money_with_wings: You want to try an agent that edits your own files, but $20/month to find out if you even like it is a hard no.
├─ :crescent_moon: You hit your plan’s limit at 11pm mid-task — flip to fcc-claude and keep going on the free backend instead of stopping.
├─ :repeat_button: You’re on your 4th regenerated API key at 2am. All four were valid. The curl would have said so in ten seconds.
├─ :robot: Claude confidently explains the fix, “writes” the file… and nothing changes on disk. That’s the tool-calling trap, not you doing it wrong.
└─ :house: You’ve got a decent GPU sitting idle — same tool, pointed at Ollama or LM Studio, fully offline, no key at all.

Fast version: curl the key → 200 → claude /logout → quit → fcc-server restart → new session. And if tools never fire, it’s the model, not you.

A key that answers 200 has nothing left to confess — everything after that is the client’s fault, not your account’s.

8 curtidas